这篇教程由浅入深学习TensorFlow MNIST 数据集写得很实用，希望能帮到您。
MNIST 数据集介绍MNIST 包含 0~9 的手写数字, 共有 60000 个训练集和 10000 个测试集. 数据的格式为单通道 28*28 的灰度图.
LeNet 模型介绍LeNet 网络最早由纽约大学的 Yann LeCun 等人于 1998 年提出, 也称 LeNet5. LeNet 是神经网络的鼻祖, 被誉为卷积神经网络的 “Hello World”.
卷积
池化 (下采样)
激活函数 (ReLU)
LeNet 逐层分析
1. 第一个卷积层
2. 第一个池化层
3. 第二个卷积层
4. 第二个池化层
5. 全连接卷积层
6. 全连接层
7. 全连接层 (输出层)
代码实现
导包from tensorflow.keras.datasets import mnistfrom matplotlib import pyplot as pltimport numpy as npimport tensorflow as tf
读取 & 查看数据# ------------------1. 读取 & 查看数据------------------# 读取数据(X_train, y_train), (X_test, y_test) = mnist.load_data()# 数据集查看print(X_train.shape) # (60000, 28, 28)print(y_train.shape) # (60000,)print(X_test.shape) # (10000, 28, 28)print(y_test.shape) # (10000,)print(type(X_train)) # <class 'numpy.ndarray'># 图片显示plt.imshow(X_train[0], cmap="Greys") # 查看第一张图片plt.show()
数据预处理# ------------------2. 数据预处理------------------# 格式转换 (将图片从28*28扩充为32*32)X_train = np.pad(X_train, ((0, 0), (2, 2), (2, 2)), "constant", constant_values=0)X_test = np.pad(X_test, ((0, 0), (2, 2), (2, 2)), "constant", constant_values=0)print(X_train.shape) # (60000, 32, 32)print(X_test.shape) # (10000, 32, 32)# 数据集格式变换X_train = X_train.astype(np.float32)X_test = X_test.astype(np.float32)# 数据正则化X_train /= 255X_test /= 255# 数据维度转换X_train = np.expand_dims(X_train, axis=-1)X_test = np.expand_dims(X_test, axis=-1)print(X_train.shape) # (60000, 32, 32, 1)print(X_test.shape) # (10000, 32, 32, 1)
模型建立# 第一个卷积层conv_layer_1 = tf.keras.layers.Conv2D(filters=6, kernel_size=(5, 5), padding="valid", activation=tf.nn.relu)# 第一个池化层pool_layer_1 = tf.keras.layers.MaxPool2D(pool_size=(2, 2), padding="same")# 第二个卷积层conv_layer_2 = tf.keras.layers.Conv2D(filters=16, kernel_size=(5, 5), padding="valid", activation=tf.nn.relu)# 第二个池化层pool_layer_2 = tf.keras.layers.MaxPool2D(padding="same")# 扁平化flatten = tf.keras.layers.Flatten()# 第一个全连接层fc_layer_1 = tf.keras.layers.Dense(units=120, activation=tf.nn.relu)# 第二个全连接层fc_layer_2 = tf.keras.layers.Dense(units=84, activation=tf.nn.softmax)# 输出层output_layer = tf.keras.layers.Dense(units=10, activation=tf.nn.softmax) 卷积 Conv2D 的用法: - filters: 卷积核个数
- kernel_size: 卷积核大小
- strides = (1, 1): 步长
- padding = “vaild”: valid 为舍弃, same 为补齐
- activation = tf.nn.relu: 激活函数
- data_format = None: 默认 channels_last
池化 AveragePooling2D 的用法: - pool_size: 池的大小
- strides = (1, 1): 步长
- padding = “vaild”: valid 为舍弃, same 为补齐
- activation = tf.nn.relu: 激活函数
- data_format = None: 默认 channels_last
全连接 Dense 的用法: - units: 输出的维度
- activation: 激活函数
- strides = (1, 1): 步长
- padding = “vaild”: valid 为舍弃, same 为补齐
- activation = tf.nn.relu: 激活函数
- data_format = None: 默认 channels_last
# 模型实例化model = tf.keras.models.Sequential([ tf.keras.layers.Conv2D(filters=6, kernel_size=(5, 5), padding='valid', activation=tf.nn.relu, input_shape=(32, 32, 1)), # relu tf.keras.layers.AveragePooling2D(pool_size=(2, 2), strides=(2, 2), padding='same'), tf.keras.layers.Conv2D(filters=16, kernel_size=(5, 5), padding='valid', activation=tf.nn.relu), tf.keras.layers.AveragePooling2D(pool_size=(2, 2), strides=(2, 2), padding='same'), tf.keras.layers.Flatten(), tf.keras.layers.Dense(units=120, activation=tf.nn.relu), tf.keras.layers.Dense(units=84, activation=tf.nn.relu), tf.keras.layers.Dense(units=10, activation=tf.nn.softmax)])# 模型展示model.summary() 输出结果: 
训练模型# ------------------4. 训练模型------------------# 设置超参数num_epochs = 10 # 训练轮数batch_size = 1000 # 批次大小learning_rate = 0.001 # 学习率 # 定义优化器adam_optimizer = tf.keras.optimizers.Adam(learning_rate)model.compile(optimizer=adam_optimizer,loss=tf.keras.losses.sparse_categorical_crossentropy,metrics=['accuracy']) complie 的用法: - optimizer: 优化器
- loss: 损失函数
- metrics: 评价
with tf.Session() as sess: # 初始化所有变量 init = tf.global_variables_initializer() sess.run(init) model.fit(x=X_train,y=y_train,batch_size=batch_size,epochs=num_epochs) # 评估指标 print(model.evaluate(X_test, y_test)) # loss value & metrics values 输出结果: 
fit 的用法: - x: 训练集
- y: 测试集
- batch_size: 批次大小
- enpochs: 训练遍数
保存模型# ------------------5. 保存模型------------------model.save('lenet_model.h5')
流程总结
完整代码from tensorflow.keras.datasets import mnistfrom matplotlib import pyplot as pltimport numpy as npimport tensorflow as tf# ------------------1. 读取 & 查看数据------------------# 读取数据(X_train, y_train), (X_test, y_test) = mnist.load_data()# 数据集查看print(X_train.shape) # (60000, 28, 28)print(y_train.shape) # (60000,)print(X_test.shape) # (10000, 28, 28)print(y_test.shape) # (10000,)print(type(X_train)) # <class 'numpy.ndarray'># 图片显示plt.imshow(X_train[0], cmap="Greys") # 查看第一张图片plt.show()# ------------------2. 数据预处理------------------# 格式转换 (将图片从28*28扩充为32*32)X_train = np.pad(X_train, ((0, 0), (2, 2), (2, 2)), "constant", constant_values=0)X_test = np.pad(X_test, ((0, 0), (2, 2), (2, 2)), "constant", constant_values=0)print(X_train.shape) # (60000, 32, 32)print(X_test.shape) # (10000, 32, 32)# 数据集格式变换X_train = X_train.astype(np.float32)X_test = X_test.astype(np.float32)# 数据正则化X_train /= 255X_test /= 255# 数据维度转换X_train = np.expand_dims(X_train, axis=-1)X_test = np.expand_dims(X_test, axis=-1)print(X_train.shape) # (60000, 32, 32, 1)print(X_test.shape) # (10000, 32, 32, 1)# ------------------3. 模型建立------------------# 第一个卷积层conv_layer_1 = tf.keras.layers.Conv2D(filters=6, kernel_size=(5, 5), padding="valid", activation=tf.nn.relu)# 第一个池化层pool_layer_1 = tf.keras.layers.MaxPool2D(pool_size=(2, 2), padding="same")# 第二个卷积层conv_layer_2 = tf.keras.layers.Conv2D(filters=16, kernel_size=(5, 5), padding="valid", activation=tf.nn.relu)# 第二个池化层pool_layer_2 = tf.keras.layers.MaxPool2D(padding="same")# 扁平化flatten = tf.keras.layers.Flatten()# 第一个全连接层fc_layer_1 = tf.keras.layers.Dense(units=120, activation=tf.nn.relu)# 第二个全连接层fc_layer_2 = tf.keras.layers.Dense(units=84, activation=tf.nn.softmax)# 输出层output_layer = tf.keras.layers.Dense(units=10, activation=tf.nn.softmax)# 模型实例化model = tf.keras.models.Sequential([ tf.keras.layers.Conv2D(filters=6, kernel_size=(5, 5), padding='valid', activation=tf.nn.relu, input_shape=(32, 32, 1)), # relu tf.keras.layers.AveragePooling2D(pool_size=(2, 2), strides=(2, 2), padding='same'), tf.keras.layers.Conv2D(filters=16, kernel_size=(5, 5), padding='valid', activation=tf.nn.relu), tf.keras.layers.AveragePooling2D(pool_size=(2, 2), strides=(2, 2), padding='same'), tf.keras.layers.Flatten(), tf.keras.layers.Dense(units=120, activation=tf.nn.relu), tf.keras.layers.Dense(units=84, activation=tf.nn.relu), tf.keras.layers.Dense(units=10, activation=tf.nn.softmax)])# 模型展示model.summary()# ------------------4. 训练模型------------------# 设置超参数num_epochs = 10 # 训练轮数batch_size = 1000 # 批次大小learning_rate = 0.001 # 学习率# 定义优化器adam_optimizer = tf.keras.optimizers.Adam(learning_rate)model.compile(optimizer=adam_optimizer,loss=tf.keras.losses.sparse_categorical_crossentropy,metrics=['accuracy'])with tf.Session() as sess: # 初始化所有变量 init = tf.global_variables_initializer() sess.run(init) model.fit(x=X_train,y=y_train,batch_size=batch_size,epochs=num_epochs) # 评估指标 print(model.evaluate(X_test, y_test)) # loss value & metrics values# ------------------5. 保存模型------------------model.save('lenet_model.h5')到此这篇关于由浅入深学习TensorFlow MNIST 数据集的文章就介绍到这了,更多相关TensorFlow MNIST 数据集内容请搜索51zixue.net以前的文章或继续浏览下面的相关文章希望大家以后多多支持51zixue.net！
详细介绍Python中的set集合
PyTorch一小时掌握之神经网络分类篇 |
